Isaac Corley

This seems like 2 separate problems. 1. Dealing with sampling from imbalanced datasets 2. You are trying to remove areas where a value in a mask is zero. Could a...

I went down the torchvision.detection rabbit hole awhile back. I think my only complaint with it was that they don't support negative sample images that don't have any objects in...

Also I believe they added support for constructing a resnet fpn backbone from a pretrained torchvision resnet model. @calebrob6 and @anthonymlortiz, this might be of interest because we could add...

> I really wish `torchvision` would add support for oriented/rotated bounding boxes i.e. `(x, y, w, h, a)`. Orientation is a significant factor when you're dealing with object detection in...

Maybe instead of try/except we should check if the datamodule has a plot method. Something like: if isinstance(getattr(datamodule, "plot"), Callable). Then in the test we can override the plot method...

> @isaaccorley does this need a predict step? Ideally yes, we can have a predict step that returns the predicted boxes and class labels per sample.

PyTorch Lightning automatically wraps samplers as DistributedSamplers so we don't need to handle any of this since we use PL. You would only need to mess with this if you...

Adding a set_epoch method to our samplers wouldn't actually solve this. The above links use DistributedSamplers which splits up dataset indices to be sampled across nodes/gpus. I've done this for...

An alternative could be to plot a false color image from a user defined subset of the bands in the image (basically a user defines indices like [0, 1, 2])...

Should we actually have a task for binary segmentation with sigmoid outputs where 0 presumably means background or should we force binary datasets to have a background class so everything...